Monthly Temperature Trends 🌡️📈¶

This project analyzes monthly temperature data from 1901 to 2017 using pandas and seaborn. It transforms wide-format climate data into a tidy format for time series visualization and seasonal trend analysis.

Files Included¶

  • monthly-temperature-trends.ipynb: Jupyter notebook with full analysis
  • monthly-temperature-trends.html: Static HTML version for preview
  • temp.csv: Source temperature data
  • thumbnail.png: Visual summary for README

Highlights¶

  • Data reshaping using pd.melt() for tidy time series
  • Monthly temperature trends across decades
  • Seasonal variation visualization
In [1]:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
In [2]:
temp = pd.read_csv("temp.csv")
In [3]:
temp.head()
Out[3]:
Unnamed: 0 YEAR JAN FEB MAR APR MAY JUN JUL AUG SEP OCT NOV DEC
0 0 1901 17.99 19.43 23.49 26.41 28.28 28.60 27.49 26.98 26.26 25.08 21.73 18.95
1 1 1902 19.00 20.39 24.10 26.54 28.68 28.44 27.29 27.05 25.95 24.37 21.33 18.78
2 2 1903 18.32 19.79 22.46 26.03 27.93 28.41 28.04 26.63 26.34 24.57 20.96 18.29
3 3 1904 17.77 19.39 22.95 26.73 27.83 27.85 26.84 26.73 25.84 24.36 21.07 18.84
4 4 1905 17.40 17.79 21.78 24.84 28.32 28.69 27.67 27.47 26.29 26.16 22.07 18.71
In [4]:
temp = pd.read_csv("temp.csv", index_col = 0)
In [5]:
temp.head()
Out[5]:
YEAR JAN FEB MAR APR MAY JUN JUL AUG SEP OCT NOV DEC
0 1901 17.99 19.43 23.49 26.41 28.28 28.60 27.49 26.98 26.26 25.08 21.73 18.95
1 1902 19.00 20.39 24.10 26.54 28.68 28.44 27.29 27.05 25.95 24.37 21.33 18.78
2 1903 18.32 19.79 22.46 26.03 27.93 28.41 28.04 26.63 26.34 24.57 20.96 18.29
3 1904 17.77 19.39 22.95 26.73 27.83 27.85 26.84 26.73 25.84 24.36 21.07 18.84
4 1905 17.40 17.79 21.78 24.84 28.32 28.69 27.67 27.47 26.29 26.16 22.07 18.71
In [6]:
temp.shape
Out[6]:
(117, 13)
In [7]:
# temp.T
In [8]:
# temp.transpose()
In [9]:
# pd.melt(temp,id_vars = "YEAR",value_vars = temp.columns[1:])

df = pd.melt(temp,id_vars = "YEAR")
In [10]:
df
Out[10]:
YEAR variable value
0 1901 JAN 17.99
1 1902 JAN 19.00
2 1903 JAN 18.32
3 1904 JAN 17.77
4 1905 JAN 17.40
... ... ... ...
1399 2013 DEC 19.69
1400 2014 DEC 19.50
1401 2015 DEC 20.21
1402 2016 DEC 21.89
1403 2017 DEC 21.47

1404 rows × 3 columns

In [11]:
117*12
Out[11]:
1404
In [12]:
df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1404 entries, 0 to 1403
Data columns (total 3 columns):
 #   Column    Non-Null Count  Dtype  
---  ------    --------------  -----  
 0   YEAR      1404 non-null   int64  
 1   variable  1404 non-null   object 
 2   value     1404 non-null   float64
dtypes: float64(1), int64(1), object(1)
memory usage: 33.0+ KB
In [13]:
date = df["variable"]+ " " + df["YEAR"].astype(str)
In [14]:
df["Date"] = pd.to_datetime(date)

C:\Users\cpaim\AppData\Local\Temp\ipykernel_14036\2086187362.py:1: UserWarning: Could not infer format, so each element will be parsed individually, falling back to `dateutil`. To ensure parsing is consistent and as-expected, please specify a format.
  df["Date"] = pd.to_datetime(date)
In [15]:
df
Out[15]:
YEAR variable value Date
0 1901 JAN 17.99 1901-01-01
1 1902 JAN 19.00 1902-01-01
2 1903 JAN 18.32 1903-01-01
3 1904 JAN 17.77 1904-01-01
4 1905 JAN 17.40 1905-01-01
... ... ... ... ...
1399 2013 DEC 19.69 2013-12-01
1400 2014 DEC 19.50 2014-12-01
1401 2015 DEC 20.21 2015-12-01
1402 2016 DEC 21.89 2016-12-01
1403 2017 DEC 21.47 2017-12-01

1404 rows × 4 columns

In [16]:
df.sort_values("Date", inplace = True)
In [17]:
df
Out[17]:
YEAR variable value Date
0 1901 JAN 17.99 1901-01-01
117 1901 FEB 19.43 1901-02-01
234 1901 MAR 23.49 1901-03-01
351 1901 APR 26.41 1901-04-01
468 1901 MAY 28.28 1901-05-01
... ... ... ... ...
935 2017 AUG 28.12 2017-08-01
1052 2017 SEP 28.11 2017-09-01
1169 2017 OCT 27.24 2017-10-01
1286 2017 NOV 23.92 2017-11-01
1403 2017 DEC 21.47 2017-12-01

1404 rows × 4 columns

In [18]:
df.reset_index(drop = True, inplace = True)
In [19]:
df.head()
Out[19]:
YEAR variable value Date
0 1901 JAN 17.99 1901-01-01
1 1901 FEB 19.43 1901-02-01
2 1901 MAR 23.49 1901-03-01
3 1901 APR 26.41 1901-04-01
4 1901 MAY 28.28 1901-05-01
In [20]:
df.columns
Out[20]:
Index(['YEAR', 'variable', 'value', 'Date'], dtype='object')
In [21]:
df.columns = ['Year', 'Month', 'Temprature', 'Date']
In [22]:
df
Out[22]:
Year Month Temprature Date
0 1901 JAN 17.99 1901-01-01
1 1901 FEB 19.43 1901-02-01
2 1901 MAR 23.49 1901-03-01
3 1901 APR 26.41 1901-04-01
4 1901 MAY 28.28 1901-05-01
... ... ... ... ...
1399 2017 AUG 28.12 2017-08-01
1400 2017 SEP 28.11 2017-09-01
1401 2017 OCT 27.24 2017-10-01
1402 2017 NOV 23.92 2017-11-01
1403 2017 DEC 21.47 2017-12-01

1404 rows × 4 columns

In [23]:
df = df[['Date','Year', 'Month', 'Temprature' ]]
In [24]:
df
Out[24]:
Date Year Month Temprature
0 1901-01-01 1901 JAN 17.99
1 1901-02-01 1901 FEB 19.43
2 1901-03-01 1901 MAR 23.49
3 1901-04-01 1901 APR 26.41
4 1901-05-01 1901 MAY 28.28
... ... ... ... ...
1399 2017-08-01 2017 AUG 28.12
1400 2017-09-01 2017 SEP 28.11
1401 2017-10-01 2017 OCT 27.24
1402 2017-11-01 2017 NOV 23.92
1403 2017-12-01 2017 DEC 21.47

1404 rows × 4 columns

In [25]:
# plotly
In [26]:
# !pip install plotly
In [27]:
mx = df["Temprature"].max()
mx
Out[27]:
30.78
In [28]:
import plotly.express as px
import plotly.graph_objects as go
In [29]:
# fig = plt.figure(figsize = (12,5))
fig = go.Figure(layout = go.Layout(yaxis = {"range":[0, mx+1]}))
In [30]:
fig = px.box(df, "Month", "Temprature")
fig.update_layout(title = "Montly Temprature over years")
fig.show()
In [31]:
# plt.subplot(3,4,1)
In [32]:
# plt.save_fig()
# fig.save_fig()
fig = px.line(df, "Year","Temprature", facet_col = "Month", facet_col_wrap = 4)
fig.show()
In [33]:
winter = ["JAN", "FEB", "DEC"]
summer = ["MAR", "APR","MAY"]
monsoon = ["JUN","JUL","AUG","SEP"]
autumn = ["OCT","NOV"]
In [34]:
temp["Winter"] = temp[winter].mean(axis = 1)
temp["Summer"] = temp[summer].mean(axis = 1)
temp["Monsoon"] = temp[monsoon].mean(axis = 1)
temp["Autumn"] = temp[autumn].mean(axis = 1)
In [35]:
temp
Out[35]:
YEAR JAN FEB MAR APR MAY JUN JUL AUG SEP OCT NOV DEC Winter Summer Monsoon Autumn
0 1901 17.99 19.43 23.49 26.41 28.28 28.60 27.49 26.98 26.26 25.08 21.73 18.95 18.790000 26.060000 27.3325 23.405
1 1902 19.00 20.39 24.10 26.54 28.68 28.44 27.29 27.05 25.95 24.37 21.33 18.78 19.390000 26.440000 27.1825 22.850
2 1903 18.32 19.79 22.46 26.03 27.93 28.41 28.04 26.63 26.34 24.57 20.96 18.29 18.800000 25.473333 27.3550 22.765
3 1904 17.77 19.39 22.95 26.73 27.83 27.85 26.84 26.73 25.84 24.36 21.07 18.84 18.666667 25.836667 26.8150 22.715
4 1905 17.40 17.79 21.78 24.84 28.32 28.69 27.67 27.47 26.29 26.16 22.07 18.71 17.966667 24.980000 27.5300 24.115
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
112 2013 18.88 21.07 24.53 26.97 29.06 28.24 27.50 27.22 26.87 25.63 22.18 19.69 19.880000 26.853333 27.4575 23.905
113 2014 18.81 20.35 23.34 26.91 28.45 29.42 28.07 27.42 26.61 25.38 22.53 19.50 19.553333 26.233333 27.8800 23.955
114 2015 19.02 21.23 23.52 26.52 28.82 28.15 28.03 27.64 27.04 25.82 22.95 20.21 20.153333 26.286667 27.7150 24.385
115 2016 20.92 23.58 26.61 29.56 30.41 29.70 28.18 28.17 27.72 26.81 23.90 21.89 22.130000 28.860000 28.4425 25.355
116 2017 20.59 23.08 25.58 29.17 30.47 29.44 28.31 28.12 28.11 27.24 23.92 21.47 21.713333 28.406667 28.4950 25.580

117 rows × 17 columns

In [36]:
temp.columns
Out[36]:
Index(['YEAR', 'JAN', 'FEB', 'MAR', 'APR', 'MAY', 'JUN', 'JUL', 'AUG', 'SEP',
       'OCT', 'NOV', 'DEC', 'Winter', 'Summer', 'Monsoon', 'Autumn'],
      dtype='object')
In [37]:
season = temp[['YEAR','Winter', 'Summer', 'Monsoon', 'Autumn']]
In [38]:
season
Out[38]:
YEAR Winter Summer Monsoon Autumn
0 1901 18.790000 26.060000 27.3325 23.405
1 1902 19.390000 26.440000 27.1825 22.850
2 1903 18.800000 25.473333 27.3550 22.765
3 1904 18.666667 25.836667 26.8150 22.715
4 1905 17.966667 24.980000 27.5300 24.115
... ... ... ... ... ...
112 2013 19.880000 26.853333 27.4575 23.905
113 2014 19.553333 26.233333 27.8800 23.955
114 2015 20.153333 26.286667 27.7150 24.385
115 2016 22.130000 28.860000 28.4425 25.355
116 2017 21.713333 28.406667 28.4950 25.580

117 rows × 5 columns

In [39]:
season = pd.melt(season, id_vars = "YEAR")
In [40]:
season
Out[40]:
YEAR variable value
0 1901 Winter 18.790000
1 1902 Winter 19.390000
2 1903 Winter 18.800000
3 1904 Winter 18.666667
4 1905 Winter 17.966667
... ... ... ...
463 2013 Autumn 23.905000
464 2014 Autumn 23.955000
465 2015 Autumn 24.385000
466 2016 Autumn 25.355000
467 2017 Autumn 25.580000

468 rows × 3 columns

In [41]:
season.columns
Out[41]:
Index(['YEAR', 'variable', 'value'], dtype='object')
In [42]:
season.columns = ['Year', 'Season', 'Avg_Temp']
In [43]:
season
Out[43]:
Year Season Avg_Temp
0 1901 Winter 18.790000
1 1902 Winter 19.390000
2 1903 Winter 18.800000
3 1904 Winter 18.666667
4 1905 Winter 17.966667
... ... ... ...
463 2013 Autumn 23.905000
464 2014 Autumn 23.955000
465 2015 Autumn 24.385000
466 2016 Autumn 25.355000
467 2017 Autumn 25.580000

468 rows × 3 columns

In [44]:
fig = px.scatter(season, "Year", "Avg_Temp", facet_col = "Season", facet_col_wrap = 2,
                trendline = "ols")
fig.show()
In [45]:
df.head()
Out[45]:
Date Year Month Temprature
0 1901-01-01 1901 JAN 17.99
1 1901-02-01 1901 FEB 19.43
2 1901-03-01 1901 MAR 23.49
3 1901-04-01 1901 APR 26.41
4 1901-05-01 1901 MAY 28.28
In [46]:
px.scatter(df,"Month", "Temprature", animation_frame = "Year", size = "Temprature")
In [47]:
temp
Out[47]:
YEAR JAN FEB MAR APR MAY JUN JUL AUG SEP OCT NOV DEC Winter Summer Monsoon Autumn
0 1901 17.99 19.43 23.49 26.41 28.28 28.60 27.49 26.98 26.26 25.08 21.73 18.95 18.790000 26.060000 27.3325 23.405
1 1902 19.00 20.39 24.10 26.54 28.68 28.44 27.29 27.05 25.95 24.37 21.33 18.78 19.390000 26.440000 27.1825 22.850
2 1903 18.32 19.79 22.46 26.03 27.93 28.41 28.04 26.63 26.34 24.57 20.96 18.29 18.800000 25.473333 27.3550 22.765
3 1904 17.77 19.39 22.95 26.73 27.83 27.85 26.84 26.73 25.84 24.36 21.07 18.84 18.666667 25.836667 26.8150 22.715
4 1905 17.40 17.79 21.78 24.84 28.32 28.69 27.67 27.47 26.29 26.16 22.07 18.71 17.966667 24.980000 27.5300 24.115
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
112 2013 18.88 21.07 24.53 26.97 29.06 28.24 27.50 27.22 26.87 25.63 22.18 19.69 19.880000 26.853333 27.4575 23.905
113 2014 18.81 20.35 23.34 26.91 28.45 29.42 28.07 27.42 26.61 25.38 22.53 19.50 19.553333 26.233333 27.8800 23.955
114 2015 19.02 21.23 23.52 26.52 28.82 28.15 28.03 27.64 27.04 25.82 22.95 20.21 20.153333 26.286667 27.7150 24.385
115 2016 20.92 23.58 26.61 29.56 30.41 29.70 28.18 28.17 27.72 26.81 23.90 21.89 22.130000 28.860000 28.4425 25.355
116 2017 20.59 23.08 25.58 29.17 30.47 29.44 28.31 28.12 28.11 27.24 23.92 21.47 21.713333 28.406667 28.4950 25.580

117 rows × 17 columns

In [48]:
temp.columns
Out[48]:
Index(['YEAR', 'JAN', 'FEB', 'MAR', 'APR', 'MAY', 'JUN', 'JUL', 'AUG', 'SEP',
       'OCT', 'NOV', 'DEC', 'Winter', 'Summer', 'Monsoon', 'Autumn'],
      dtype='object')
In [49]:
tm = ['JAN', 'FEB', 'MAR', 'APR', 'MAY', 'JUN', 'JUL', 'AUG', 'SEP','OCT', 'NOV', 'DEC']
In [50]:
temp["Yearly_Mean"] = temp[tm].mean(axis = 1)
In [51]:
temp
Out[51]:
YEAR JAN FEB MAR APR MAY JUN JUL AUG SEP OCT NOV DEC Winter Summer Monsoon Autumn Yearly_Mean
0 1901 17.99 19.43 23.49 26.41 28.28 28.60 27.49 26.98 26.26 25.08 21.73 18.95 18.790000 26.060000 27.3325 23.405 24.224167
1 1902 19.00 20.39 24.10 26.54 28.68 28.44 27.29 27.05 25.95 24.37 21.33 18.78 19.390000 26.440000 27.1825 22.850 24.326667
2 1903 18.32 19.79 22.46 26.03 27.93 28.41 28.04 26.63 26.34 24.57 20.96 18.29 18.800000 25.473333 27.3550 22.765 23.980833
3 1904 17.77 19.39 22.95 26.73 27.83 27.85 26.84 26.73 25.84 24.36 21.07 18.84 18.666667 25.836667 26.8150 22.715 23.850000
4 1905 17.40 17.79 21.78 24.84 28.32 28.69 27.67 27.47 26.29 26.16 22.07 18.71 17.966667 24.980000 27.5300 24.115 23.932500
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
112 2013 18.88 21.07 24.53 26.97 29.06 28.24 27.50 27.22 26.87 25.63 22.18 19.69 19.880000 26.853333 27.4575 23.905 24.820000
113 2014 18.81 20.35 23.34 26.91 28.45 29.42 28.07 27.42 26.61 25.38 22.53 19.50 19.553333 26.233333 27.8800 23.955 24.732500
114 2015 19.02 21.23 23.52 26.52 28.82 28.15 28.03 27.64 27.04 25.82 22.95 20.21 20.153333 26.286667 27.7150 24.385 24.912500
115 2016 20.92 23.58 26.61 29.56 30.41 29.70 28.18 28.17 27.72 26.81 23.90 21.89 22.130000 28.860000 28.4425 25.355 26.454167
116 2017 20.59 23.08 25.58 29.17 30.47 29.44 28.31 28.12 28.11 27.24 23.92 21.47 21.713333 28.406667 28.4950 25.580 26.291667

117 rows × 18 columns

In [52]:
fig = go.Figure(data = [go.Scatter(x = temp["YEAR"], y = temp["Yearly_Mean"],mode = "lines"),
                       go.Scatter(x = temp["YEAR"], y = temp["Yearly_Mean"],mode = "markers")])
fig.update_layout(xaxis_title = "Year", yaxis_title = "Mean Temp", title = "XYZ")

fig.show()
In [53]:
df
Out[53]:
Date Year Month Temprature
0 1901-01-01 1901 JAN 17.99
1 1901-02-01 1901 FEB 19.43
2 1901-03-01 1901 MAR 23.49
3 1901-04-01 1901 APR 26.41
4 1901-05-01 1901 MAY 28.28
... ... ... ... ...
1399 2017-08-01 2017 AUG 28.12
1400 2017-09-01 2017 SEP 28.11
1401 2017-10-01 2017 OCT 27.24
1402 2017-11-01 2017 NOV 23.92
1403 2017-12-01 2017 DEC 21.47

1404 rows × 4 columns

In [54]:
df.columns
Out[54]:
Index(['Date', 'Year', 'Month', 'Temprature'], dtype='object')
In [55]:
ml = df[['Year', 'Month', 'Temprature']]
In [56]:
ml.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1404 entries, 0 to 1403
Data columns (total 3 columns):
 #   Column      Non-Null Count  Dtype  
---  ------      --------------  -----  
 0   Year        1404 non-null   int64  
 1   Month       1404 non-null   object 
 2   Temprature  1404 non-null   float64
dtypes: float64(1), int64(1), object(1)
memory usage: 33.0+ KB
In [57]:
data = pd.get_dummies(ml)
In [58]:
data.head()
Out[58]:
Year Temprature Month_APR Month_AUG Month_DEC Month_FEB Month_JAN Month_JUL Month_JUN Month_MAR Month_MAY Month_NOV Month_OCT Month_SEP
0 1901 17.99 False False False False True False False False False False False False
1 1901 19.43 False False False True False False False False False False False False
2 1901 23.49 False False False False False False False True False False False False
3 1901 26.41 True False False False False False False False False False False False
4 1901 28.28 False False False False False False False False True False False False
In [59]:
x = data.drop("Temprature", axis = 1).copy()
y = data["Temprature"]
In [60]:
from sklearn.ensemble import RandomForestRegressor
from sklearn.tree import DecisionTreeRegressor
from sklearn.model_selection import train_test_split
In [61]:
x_train, x_test,y_train, y_test = train_test_split(x,y, test_size =0.3)
In [62]:
print(x_train.shape, x_test.shape,y_train.shape, y_test.shape)

(982, 13) (422, 13) (982,) (422,)
In [63]:
dtr = DecisionTreeRegressor()
In [64]:
dtr.fit(x_train, y_train)
Out[64]:
DecisionTreeRegressor()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
DecisionTreeRegressor()
In [65]:
predict = dtr.predict(x_test)
In [66]:
from sklearn.metrics import accuracy_score, r2_score
In [67]:
r2_score(predict, y_test)
Out[67]:
0.9644413279756798
In [68]:
temp["YEAR"].max()
Out[68]:
2017
In [69]:
x_test
Out[69]:
Year Month_APR Month_AUG Month_DEC Month_FEB Month_JAN Month_JUL Month_JUN Month_MAR Month_MAY Month_NOV Month_OCT Month_SEP
1212 2002 False False False False True False False False False False False False
527 1944 False False True False False False False False False False False False
1333 2012 False False False True False False False False False False False False
1353 2013 False False False False False False False False False False True False
1291 2008 False True False False False False False False False False False False
... ... ... ... ... ... ... ... ... ... ... ... ... ...
294 1925 False False False False False True False False False False False False
571 1948 False True False False False False False False False False False False
39 1904 True False False False False False False False False False False False
420 1936 False False False False True False False False False False False False
873 1973 False False False False False False False False False False True False

422 rows × 13 columns

In [70]:
df
Out[70]:
Date Year Month Temprature
0 1901-01-01 1901 JAN 17.99
1 1901-02-01 1901 FEB 19.43
2 1901-03-01 1901 MAR 23.49
3 1901-04-01 1901 APR 26.41
4 1901-05-01 1901 MAY 28.28
... ... ... ... ...
1399 2017-08-01 2017 AUG 28.12
1400 2017-09-01 2017 SEP 28.11
1401 2017-10-01 2017 OCT 27.24
1402 2017-11-01 2017 NOV 23.92
1403 2017-12-01 2017 DEC 21.47

1404 rows × 4 columns

In [71]:
next_year = df[df["Year"]==2017][["Year","Month"]]
next_year["Year"] = next_year["Year"].replace(2017, 2018)
In [72]:
next_year
Out[72]:
Year Month
1392 2018 JAN
1393 2018 FEB
1394 2018 MAR
1395 2018 APR
1396 2018 MAY
1397 2018 JUN
1398 2018 JUL
1399 2018 AUG
1400 2018 SEP
1401 2018 OCT
1402 2018 NOV
1403 2018 DEC
In [73]:
test = pd.get_dummies(next_year)
In [74]:
dtr.predict(test)
Out[74]:
array([19.02, 23.08, 25.58, 29.17, 30.41, 29.44, 28.31, 28.17, 28.11,
       27.24, 23.92, 21.47])
In [75]:
np.array(df[df["Year"]==2017]["Temprature"])
Out[75]:
array([20.59, 23.08, 25.58, 29.17, 30.47, 29.44, 28.31, 28.12, 28.11,
       27.24, 23.92, 21.47])
In [76]:
df
Out[76]:
Date Year Month Temprature
0 1901-01-01 1901 JAN 17.99
1 1901-02-01 1901 FEB 19.43
2 1901-03-01 1901 MAR 23.49
3 1901-04-01 1901 APR 26.41
4 1901-05-01 1901 MAY 28.28
... ... ... ... ...
1399 2017-08-01 2017 AUG 28.12
1400 2017-09-01 2017 SEP 28.11
1401 2017-10-01 2017 OCT 27.24
1402 2017-11-01 2017 NOV 23.92
1403 2017-12-01 2017 DEC 21.47

1404 rows × 4 columns

In [77]:
season
Out[77]:
Year Season Avg_Temp
0 1901 Winter 18.790000
1 1902 Winter 19.390000
2 1903 Winter 18.800000
3 1904 Winter 18.666667
4 1905 Winter 17.966667
... ... ... ...
463 2013 Autumn 23.905000
464 2014 Autumn 23.955000
465 2015 Autumn 24.385000
466 2016 Autumn 25.355000
467 2017 Autumn 25.580000

468 rows × 3 columns

In [78]:
temp
Out[78]:
YEAR JAN FEB MAR APR MAY JUN JUL AUG SEP OCT NOV DEC Winter Summer Monsoon Autumn Yearly_Mean
0 1901 17.99 19.43 23.49 26.41 28.28 28.60 27.49 26.98 26.26 25.08 21.73 18.95 18.790000 26.060000 27.3325 23.405 24.224167
1 1902 19.00 20.39 24.10 26.54 28.68 28.44 27.29 27.05 25.95 24.37 21.33 18.78 19.390000 26.440000 27.1825 22.850 24.326667
2 1903 18.32 19.79 22.46 26.03 27.93 28.41 28.04 26.63 26.34 24.57 20.96 18.29 18.800000 25.473333 27.3550 22.765 23.980833
3 1904 17.77 19.39 22.95 26.73 27.83 27.85 26.84 26.73 25.84 24.36 21.07 18.84 18.666667 25.836667 26.8150 22.715 23.850000
4 1905 17.40 17.79 21.78 24.84 28.32 28.69 27.67 27.47 26.29 26.16 22.07 18.71 17.966667 24.980000 27.5300 24.115 23.932500
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
112 2013 18.88 21.07 24.53 26.97 29.06 28.24 27.50 27.22 26.87 25.63 22.18 19.69 19.880000 26.853333 27.4575 23.905 24.820000
113 2014 18.81 20.35 23.34 26.91 28.45 29.42 28.07 27.42 26.61 25.38 22.53 19.50 19.553333 26.233333 27.8800 23.955 24.732500
114 2015 19.02 21.23 23.52 26.52 28.82 28.15 28.03 27.64 27.04 25.82 22.95 20.21 20.153333 26.286667 27.7150 24.385 24.912500
115 2016 20.92 23.58 26.61 29.56 30.41 29.70 28.18 28.17 27.72 26.81 23.90 21.89 22.130000 28.860000 28.4425 25.355 26.454167
116 2017 20.59 23.08 25.58 29.17 30.47 29.44 28.31 28.12 28.11 27.24 23.92 21.47 21.713333 28.406667 28.4950 25.580 26.291667

117 rows × 18 columns

In [79]:
temp.columns
Out[79]:
Index(['YEAR', 'JAN', 'FEB', 'MAR', 'APR', 'MAY', 'JUN', 'JUL', 'AUG', 'SEP',
       'OCT', 'NOV', 'DEC', 'Winter', 'Summer', 'Monsoon', 'Autumn',
       'Yearly_Mean'],
      dtype='object')
In [80]:
d = temp[['YEAR', 'JAN', 'FEB', 'MAR', 'APR', 'MAY', 'JUN', 'JUL', 'AUG', 'SEP',
       'OCT', 'NOV', 'DEC']]
In [81]:
temp
Out[81]:
YEAR JAN FEB MAR APR MAY JUN JUL AUG SEP OCT NOV DEC Winter Summer Monsoon Autumn Yearly_Mean
0 1901 17.99 19.43 23.49 26.41 28.28 28.60 27.49 26.98 26.26 25.08 21.73 18.95 18.790000 26.060000 27.3325 23.405 24.224167
1 1902 19.00 20.39 24.10 26.54 28.68 28.44 27.29 27.05 25.95 24.37 21.33 18.78 19.390000 26.440000 27.1825 22.850 24.326667
2 1903 18.32 19.79 22.46 26.03 27.93 28.41 28.04 26.63 26.34 24.57 20.96 18.29 18.800000 25.473333 27.3550 22.765 23.980833
3 1904 17.77 19.39 22.95 26.73 27.83 27.85 26.84 26.73 25.84 24.36 21.07 18.84 18.666667 25.836667 26.8150 22.715 23.850000
4 1905 17.40 17.79 21.78 24.84 28.32 28.69 27.67 27.47 26.29 26.16 22.07 18.71 17.966667 24.980000 27.5300 24.115 23.932500
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
112 2013 18.88 21.07 24.53 26.97 29.06 28.24 27.50 27.22 26.87 25.63 22.18 19.69 19.880000 26.853333 27.4575 23.905 24.820000
113 2014 18.81 20.35 23.34 26.91 28.45 29.42 28.07 27.42 26.61 25.38 22.53 19.50 19.553333 26.233333 27.8800 23.955 24.732500
114 2015 19.02 21.23 23.52 26.52 28.82 28.15 28.03 27.64 27.04 25.82 22.95 20.21 20.153333 26.286667 27.7150 24.385 24.912500
115 2016 20.92 23.58 26.61 29.56 30.41 29.70 28.18 28.17 27.72 26.81 23.90 21.89 22.130000 28.860000 28.4425 25.355 26.454167
116 2017 20.59 23.08 25.58 29.17 30.47 29.44 28.31 28.12 28.11 27.24 23.92 21.47 21.713333 28.406667 28.4950 25.580 26.291667

117 rows × 18 columns

In [82]:
df
Out[82]:
Date Year Month Temprature
0 1901-01-01 1901 JAN 17.99
1 1901-02-01 1901 FEB 19.43
2 1901-03-01 1901 MAR 23.49
3 1901-04-01 1901 APR 26.41
4 1901-05-01 1901 MAY 28.28
... ... ... ... ...
1399 2017-08-01 2017 AUG 28.12
1400 2017-09-01 2017 SEP 28.11
1401 2017-10-01 2017 OCT 27.24
1402 2017-11-01 2017 NOV 23.92
1403 2017-12-01 2017 DEC 21.47

1404 rows × 4 columns

In [83]:
d = {"Month":df["Month"].unique(),"Temprature" :dtr.predict(test)}
In [84]:
d_2018 = pd.DataFrame(d)
In [85]:
d_2018
Out[85]:
Month Temprature
0 JAN 19.02
1 FEB 23.08
2 MAR 25.58
3 APR 29.17
4 MAY 30.41
5 JUN 29.44
6 JUL 28.31
7 AUG 28.17
8 SEP 28.11
9 OCT 27.24
10 NOV 23.92
11 DEC 21.47
In [86]:
final = pd.concat([df,d_2018], axis = 0)
In [87]:
final["Year"] = final["Year"].fillna(2018).astype(int)
In [88]:
final
Out[88]:
Date Year Month Temprature
0 1901-01-01 1901 JAN 17.99
1 1901-02-01 1901 FEB 19.43
2 1901-03-01 1901 MAR 23.49
3 1901-04-01 1901 APR 26.41
4 1901-05-01 1901 MAY 28.28
... ... ... ... ...
7 NaT 2018 AUG 28.17
8 NaT 2018 SEP 28.11
9 NaT 2018 OCT 27.24
10 NaT 2018 NOV 23.92
11 NaT 2018 DEC 21.47

1416 rows × 4 columns

In [ ]: